Fig. 1From: High-dimensional neural feature design for layer-wise reduction of training costTraining and testing accuracy against size of one instance of HNF. Size of an L-layer HNF is represented by the number of random matrix-based nodes, counted as \(\sum _{l=1}^{L} 2 n^{(l)}\). Here, L=5 for all three datasets. The number of nodes in the first layer (2 n(1)) is set according to Table 1 for each datasetBack to article page